vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [RFC]: Pluggable KV Cache Data Types
- [XPU][Test] Fix OOT model registration in extract_hidden_states test
- [Bug][KV Offload] EAGLE volatile-tail boundary can collapse hybrid SWA replay to zero hits
- [Bug]: CuTe FA4 forward (flash_fwd.py SM80/SM120) fails on first call: NameError 'mDynamicCausal' and missing self.is_split_kv
- [Docker] Pin nixl backend to the requested nixl version
- [RFC]: Suffix decoding on GPU (`suffix_gpu`) under async scheduling, and variable draft-length scheduling for GPU-state drafters
- [Bug]: DeepSeek V4 mHC warmup is always skipped because DeepseekV4DecoderLayer has no hc_pre/hc_post attributes
- [Model] Match Qwen3.5 GDN BF16 semantics
- [feat] add torchcodec as audio loader and implement selective audio backend
- Fix/kimi nixl pp mamba
- Docs
- Python not yet supported